基于多维语义映射的关系抽取方法研究

Relation Extraction Based on Multidimensional Semantic Mapping

关系抽取旨在从句子中识别出实体对之间的关系类型。在关系抽取领域,目前主流的方法都使用了深度学习方法,但大部分方法在输入层没有对词向量进行深层次的讨论。针对这一不足,提出了一种基于多维语义映射的关系抽取方法,该方法的核心思想是将矩阵降维方法应用于神经网络模型输入层。通过将表示文本的词向量进行多维度的降维分解,使分解后的词向量能映射表示同一语句在不同维度上的语义信息。实验结果表明,在Chinese Literature Text和SemEval-2010 Task8数据集上F1值分别达到了75.3%和88.9%,验证了所提方法的有效性。

Relation extraction aims to identify relation types between entities from texts.In the field of relation extraction,most of existing methods use deep learning methods,but they do not have in-depth discussion of word vectors in the input layer.To further exploit word vectors,this paper proposes a relation extraction method based on multi-dimensional semantic mapping.The core idea of the method is to reduce dimensionality of text feature matrix before the word vector enters the input layer.Experimental results show that the proposed method not only can reduce dimensionality effectively,but also can represent the semantic information of the same sentence in different dimensions,with its F1 of 75.3%and 88.9%on the Chinese Literature Text and SemEval-2010 Task8 datasets,respectively.